GrepJob
OpenAI

Researcher, Agentic Post-Training

OpenAI
Apply
about 19 hours ago
San Francisco, CA, USA
Mid Level / Senior

Base Salary

$295k - $445k/yr

Responsibilities

  • Own end-to-end research and engineering projects for agentic models.
  • Decide on integrations ready for major model runs with partner teams.
  • Develop horizontal model improvements across various capabilities.
  • Build and enhance training, evaluation, grading, and data infrastructure.
  • Create evaluations and diagnostics to assess model readiness.
  • Improve feedback loops from product usage into post-training.
  • Collaborate with multiple teams to enhance model utility and reliability.

Requirements

  • Strong ML fundamentals and hands-on experience with LLMs and RL.
  • Proven engineering skills to navigate complex systems quickly.
  • Ability to manage ambiguous problems without a detailed roadmap.
  • Focus on impact over method, willing to handle essential but unglamorous tasks.
  • Excellent taste in model behavior across user-facing domains.
  • Comfortable working across research, infrastructure, data, and product boundaries.
  • Excitement for training and shipping frontier agentic models.

Categories

AI & MLBackendData Science